© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 66884
    Prev
    Next
    INDEX
    Explanations

    fingers or toes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_41_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ô
    0.42
     पटेल
    0.38
     Edison
    0.37
     Fut
    0.37
     रायपुर
    0.37
     Handles
    0.35
    핸
    0.35
    cepc
    0.35
    ்ப
    0.35
     असे
    0.35
    POSITIVE LOGITS
     fingers
    1.61
     Fingers
    1.45
    fing
    1.31
     finger
    1.27
     dedos
    1.21
    Finger
    1.17
     fing
    1.16
     doigts
    1.15
    指
    1.10
    finger
    1.09
    Activations Density 0.078%

    No Known Activations